[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240807-b4-slab-kfree_rcu-destroy-v2-2-ea79102f428c@suse.cz>
Date: Wed, 07 Aug 2024 12:31:15 +0200
From: Vlastimil Babka <vbabka@...e.cz>
To: "Paul E. McKenney" <paulmck@...nel.org>,
Joel Fernandes <joel@...lfernandes.org>,
Josh Triplett <josh@...htriplett.org>, Boqun Feng <boqun.feng@...il.com>,
Christoph Lameter <cl@...ux.com>, David Rientjes <rientjes@...gle.com>
Cc: Steven Rostedt <rostedt@...dmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Lai Jiangshan <jiangshanlai@...il.com>, Zqiang <qiang.zhang1211@...il.com>,
Julia Lawall <Julia.Lawall@...ia.fr>, Jakub Kicinski <kuba@...nel.org>,
"Jason A. Donenfeld" <Jason@...c4.com>,
"Uladzislau Rezki (Sony)" <urezki@...il.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Hyeonggon Yoo <42.hyeyoo@...il.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, rcu@...r.kernel.org,
Alexander Potapenko <glider@...gle.com>, Marco Elver <elver@...gle.com>,
Dmitry Vyukov <dvyukov@...gle.com>, kasan-dev@...glegroups.com,
Jann Horn <jannh@...gle.com>, Mateusz Guzik <mjguzik@...il.com>,
Vlastimil Babka <vbabka@...e.cz>
Subject: [PATCH v2 2/7] mm, slab: unlink slabinfo, sysfs and debugfs
immediately
kmem_cache_destroy() includes removing the associated sysfs and debugfs
directories, and the cache from the list of caches that appears in
/proc/slabinfo. Currently this might not happen immediately when:
- the cache is SLAB_TYPESAFE_BY_RCU and the cleanup is delayed,
including the directores removal
- __kmem_cache_shutdown() fails due to outstanding objects - the
directories remain indefinitely
When a cache is recreated with the same name, such as due to module
unload followed by a load, the directories will fail to be recreated for
the new instance of the cache due to the old directories being present.
The cache will also appear twice in /proc/slabinfo.
While we want to convert the SLAB_TYPESAFE_BY_RCU cleanup to be
synchronous again, the second point remains. So let's fix this first and
have the directories and slabinfo removed immediately in
kmem_cache_destroy() and regardless of __kmem_cache_shutdown() success.
This should not make debugging harder if __kmem_cache_shutdown() fails,
because a detailed report of outstanding objects is printed into dmesg
already due to the failure.
Also simplify kmem_cache_release() sysfs handling by using
__is_defined(SLAB_SUPPORTS_SYSFS).
Note the resulting code in kmem_cache_destroy() is a bit ugly but will
be further simplified - this is in order to make small bisectable steps.
Signed-off-by: Vlastimil Babka <vbabka@...e.cz>
---
mm/slab_common.c | 57 ++++++++++++++++++++++++++------------------------------
1 file changed, 26 insertions(+), 31 deletions(-)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index b76d65d7fe33..db61df3b4282 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -484,31 +484,19 @@ kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags,
}
EXPORT_SYMBOL(kmem_buckets_create);
-#ifdef SLAB_SUPPORTS_SYSFS
/*
* For a given kmem_cache, kmem_cache_destroy() should only be called
* once or there will be a use-after-free problem. The actual deletion
* and release of the kobject does not need slab_mutex or cpu_hotplug_lock
* protection. So they are now done without holding those locks.
- *
- * Note that there will be a slight delay in the deletion of sysfs files
- * if kmem_cache_release() is called indrectly from a work function.
*/
static void kmem_cache_release(struct kmem_cache *s)
{
- if (slab_state >= FULL) {
- sysfs_slab_unlink(s);
+ if (__is_defined(SLAB_SUPPORTS_SYSFS) && slab_state >= FULL)
sysfs_slab_release(s);
- } else {
+ else
slab_kmem_cache_release(s);
- }
}
-#else
-static void kmem_cache_release(struct kmem_cache *s)
-{
- slab_kmem_cache_release(s);
-}
-#endif
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
{
@@ -534,7 +522,6 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
rcu_barrier();
list_for_each_entry_safe(s, s2, &to_destroy, list) {
- debugfs_slab_release(s);
kfence_shutdown_cache(s);
kmem_cache_release(s);
}
@@ -549,8 +536,8 @@ void slab_kmem_cache_release(struct kmem_cache *s)
void kmem_cache_destroy(struct kmem_cache *s)
{
- int err = -EBUSY;
bool rcu_set;
+ int err;
if (unlikely(!s) || !kasan_check_byte(s))
return;
@@ -558,11 +545,14 @@ void kmem_cache_destroy(struct kmem_cache *s)
cpus_read_lock();
mutex_lock(&slab_mutex);
- rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU;
-
s->refcount--;
- if (s->refcount)
- goto out_unlock;
+ if (s->refcount) {
+ mutex_unlock(&slab_mutex);
+ cpus_read_unlock();
+ return;
+ }
+
+ rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU;
/* free asan quarantined objects */
kasan_cache_shutdown(s);
@@ -571,24 +561,29 @@ void kmem_cache_destroy(struct kmem_cache *s)
WARN(err, "%s %s: Slab cache still has objects when called from %pS",
__func__, s->name, (void *)_RET_IP_);
- if (err)
- goto out_unlock;
-
list_del(&s->list);
- if (rcu_set) {
- list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
- schedule_work(&slab_caches_to_rcu_destroy_work);
- } else {
+ if (!err && !rcu_set)
kfence_shutdown_cache(s);
- debugfs_slab_release(s);
- }
-out_unlock:
mutex_unlock(&slab_mutex);
cpus_read_unlock();
- if (!err && !rcu_set)
+
+ if (slab_state >= FULL)
+ sysfs_slab_unlink(s);
+ debugfs_slab_release(s);
+
+ if (err)
+ return;
+
+ if (rcu_set) {
+ mutex_lock(&slab_mutex);
+ list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
+ schedule_work(&slab_caches_to_rcu_destroy_work);
+ mutex_unlock(&slab_mutex);
+ } else {
kmem_cache_release(s);
+ }
}
EXPORT_SYMBOL(kmem_cache_destroy);
--
2.46.0
Powered by blists - more mailing lists